code_review · Git Steer MCP: Risk & Policy

WHAT IT DOES

What code_review does on Git Steer

AI agents invoke code_review to trigger actions in Git Steer. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why code_review needs a policy

This tool executes an external CLI tool (CodeRabbit) to perform analysis on repository code. While the action itself is read-heavy in nature (analyzing without modifying code), the invocation of arbitrary external tooling with potential side effects (credential usage, external service calls, local file system operations) and the ability to trigger dependent workflows or actions (per the server's autonomous nature)…

From the tool's definition Tool 'code_review' runs 'AI-powered code review using CodeRabbit CLI' on 'changes in a local git repository'. The verb 'run' and invocation of an external CLI tool (CodeRabbit) constitute code execution.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

code_review Rate-limited

code_review stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "code_review": {
      "limits": [
        {
          "counter": "code_review_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Git Steer, so you can run agents against it safely.

FAQ

Questions about code_review

What does the code_review tool do? +

Run AI-powered code review using CodeRabbit CLI. Reviews changes in a local git repository. It is categorised as a Execute tool in the Git Steer MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on code_review? +

Register the Git Steer MCP server in PolicyLayer and add a rule for code_review: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Git Steer. Nothing to install.

What risk level is code_review? +

code_review is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit code_review? +

Yes. Add a rate_limit block to the code_review rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block code_review completely? +

Set action: deny in the PolicyLayer policy for code_review. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides code_review? +

code_review is provided by the Git Steer MCP server (ry-ops/git-steer). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.